{"id":"W4387068365","doi":"10.1109/comst.2023.3319492","title":"Adversarial Attacks and Defenses in Machine Learning-Empowered Communication Systems and Networks: A Contemporary Survey","year":2023,"lang":"en","type":"article","venue":"IEEE Communications Surveys & Tutorials","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":124,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China; National Science Foundation","keywords":"Adversarial system; Computer science; Robustness (evolution); Artificial intelligence; Machine learning; Deep learning; Transferability; Categorization; Deep neural networks; Decision tree; Adversarial machine learning; Software deployment; Data science; Field (mathematics); Computer security; Software engineering","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.01873771,0.0003465942,0.0006873561,0.0004637411,0.0008198819,0.000510331,0.002498408,0.0002648635,0.000002753308],"category_scores_gemma":[0.003204429,0.0003748565,0.00005732939,0.001737022,0.0004648808,0.0009119539,0.002196112,0.0009420114,0.00002196544],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001082691,"about_ca_system_score_gemma":0.0001884786,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0127247,"about_ca_topic_score_gemma":0.002967793,"domain_scores_codex":[0.979492,0.01808774,0.000975708,0.0006203168,0.0003665793,0.0004576226],"domain_scores_gemma":[0.9861479,0.009939146,0.0005335553,0.002940724,0.0002810838,0.0001576223],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001647263,0.0002954261,0.7988695,0.00009126716,0.0002663679,0.00002927724,0.00686301,0.1593226,0.0003015363,0.02157587,0.003657069,0.008563364],"study_design_scores_gemma":[0.001989401,0.00009192894,0.2273368,0.0001628621,0.00001648939,0.00001587665,0.0002566887,0.7602785,0.000006070275,0.0004215238,0.008827593,0.0005962679],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4051644,0.04404368,0.5203539,0.0042433,0.01313383,0.0050253,0.000278045,0.004001355,0.003756161],"genre_scores_gemma":[0.9928653,0.003465591,0.00271223,0.00003162822,0.0001452912,0.0001091337,0.0004183909,0.00004583258,0.0002065507],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6009559,"threshold_uncertainty_score":0.9998704,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07554101023633406,"score_gpt":0.3193680409457303,"score_spread":0.2438270307093962,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}